from keras.models import load_model #下面报错 没有相关的提示信息？？？？？？
model = SqueezeNet()
#保存model部分 # save as JSON 保存模型的结构，而不包含其权重或配置信息
model_json = model.to_json()
# with open("model.json", "w") as json_file:
# json_file.write(model_json)
# del_json = model.to_json()
# json_file.write(model_json)
#只保存权重
model.save_weights("model.h5")
#保存model和权重
model.save('my_model.h5') # creates a HDF5 file 'my_model.h5'
del model # deletes the existing model
model = load_model(
'my_model.h5') # returns a compiled model identical to the previous one
#img = image.load_img(img_path, target_size=(224, 224)) # 加载图像，归一化大小
img = image.load_img('images/cat.jpeg', target_size=(227, 227))
x = image.img_to_array(img) # 序列化
x = np.expand_dims(x, axis=0) # 展开
x = preprocess_input(x) # 预处理到0～1
preds = model.predict(x) # 预测结果，1000维的向量
print(
class_mode='categorical')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical')
train_history = model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples / batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
model.save_weights('navigation_cnn_squeezenet_EE_2F_4class_v2.h5')
#view gradient descent
import matplotlib.pyplot as plt
def show_train_history(train_history, train, validation):
plt.plot(train_history.history[train])
plt.plot(train_history.history[validation])
plt.title('Train History')
plt.ylabel(train)
plt.xlabel('Epoch')
plt.legend(['train', 'validation'], loc='upper left')
plt.show()
target_size=(227, 227), # all images will be resized to 150x150
batch_size=batch_size,
class_mode='binary'
) # since we use binary_crossentropy loss, we need binary labels
# this is a similar generator, for validation data
validation_generator = test_datagen.flow_from_directory(path + 'valid',
target_size=(227, 227),
batch_size=batch_size,
class_mode='binary')
steps = train_generator.samples // batch_size
if steps == 0:
steps = 1
val_steps = validation_generator.samples // batch_size
if val_steps == 0:
val_steps = 1
model.fit_generator(train_generator,
steps_per_epoch=steps,
epochs=1,
validation_data=validation_generator,
validation_steps=val_steps)
model.save_weights(
'squeezecatsdogs.h5'
) # always save your weights after training or during training
